[PATCH v4 08/16] sequencer: refactor rearrange_squash() to work on a todo_list

[Alban Gruin <alban.gruin@gmail.com>]

This refactors rearrange_squash() to work on a todo_list to avoid
redundant reads and writes.  The function is renamed
todo_list_rearrange_squash().

The old version created a new buffer, which was directly written to the
disk.  This new version creates a new item list by just copying items
from the old item list, without creating a new buffer.  This eliminates
the need to reparse the todo list, but this also means its buffer cannot
be directly written to the disk.

As rebase -p still need to check the todo list from the disk, a new
function is introduced, rearrange_squash_in_todo_file().

complete_action() still uses rearrange_squash_in_todo_file() for now.
This will be changed in a future commit.

Signed-off-by: Alban Gruin <alban.gruin@gmail.com>
---
Slight rewording of the commit message and changes due to conflicts with
nd/the-index.

 builtin/rebase--interactive.c |  2 +-
 sequencer.c                   | 92 ++++++++++++++++++-----------------
 sequencer.h                   |  2 +-
 3 files changed, 49 insertions(+), 47 deletions(-)

diff --git a/builtin/rebase--interactive.c b/builtin/rebase--interactive.c
index 53056ee713..4f0eae9239 100644
--- a/builtin/rebase--interactive.c
+++ b/builtin/rebase--interactive.c
@@ -266,7 +266,7 @@ int cmd_rebase__interactive(int argc, const char **argv, const char *prefix)
 		ret = check_todo_list_from_file(the_repository);
 		break;
 	case REARRANGE_SQUASH:
-		ret = rearrange_squash(the_repository);
+		ret = rearrange_squash_in_todo_file(the_repository);
 		break;
 	case ADD_EXEC:
 		ret = sequencer_add_exec_commands(the_repository, &commands);
diff --git a/sequencer.c b/sequencer.c
index 2df64b3677..931ad9848e 100644
--- a/sequencer.c
+++ b/sequencer.c
@@ -4771,7 +4771,7 @@ int complete_action(struct repository *r, struct replay_opts *opts, unsigned fla
 	    write_message("noop\n", 5, todo_file, 0))
 		return -1;
 
-	if (autosquash && rearrange_squash(r))
+	if (autosquash && rearrange_squash_in_todo_file(r))
 		return -1;
 
 	if (commands->nr)
@@ -4877,21 +4877,13 @@ define_commit_slab(commit_todo_item, struct todo_item *);
  * message will have to be retrieved from the commit (as the oneline in the
  * script cannot be trusted) in order to normalize the autosquash arrangement.
  */
-int rearrange_squash(struct repository *r)
+static int todo_list_rearrange_squash(struct todo_list *todo_list)
 {
-	const char *todo_file = rebase_path_todo();
-	struct todo_list todo_list = TODO_LIST_INIT;
 	struct hashmap subject2item;
-	int res = 0, rearranged = 0, *next, *tail, i;
+	int rearranged = 0, *next, *tail, i, nr = 0, alloc = 0;
 	char **subjects;
 	struct commit_todo_item commit_todo;
-
-	if (strbuf_read_file_or_whine(&todo_list.buf, todo_file) < 0)
-		return -1;
-	if (todo_list_parse_insn_buffer(r, todo_list.buf.buf, &todo_list) < 0) {
-		todo_list_release(&todo_list);
-		return -1;
-	}
+	struct todo_item *items = NULL;
 
 	init_commit_todo_item(&commit_todo);
 	/*
@@ -4904,13 +4896,13 @@ int rearrange_squash(struct repository *r)
 	 * be moved to appear after the i'th.
 	 */
 	hashmap_init(&subject2item, (hashmap_cmp_fn) subject2item_cmp,
-		     NULL, todo_list.nr);
-	ALLOC_ARRAY(next, todo_list.nr);
-	ALLOC_ARRAY(tail, todo_list.nr);
-	ALLOC_ARRAY(subjects, todo_list.nr);
-	for (i = 0; i < todo_list.nr; i++) {
+		     NULL, todo_list->nr);
+	ALLOC_ARRAY(next, todo_list->nr);
+	ALLOC_ARRAY(tail, todo_list->nr);
+	ALLOC_ARRAY(subjects, todo_list->nr);
+	for (i = 0; i < todo_list->nr; i++) {
 		struct strbuf buf = STRBUF_INIT;
-		struct todo_item *item = todo_list.items + i;
+		struct todo_item *item = todo_list->items + i;
 		const char *commit_buffer, *subject, *p;
 		size_t subject_len;
 		int i2 = -1;
@@ -4923,7 +4915,6 @@ int rearrange_squash(struct repository *r)
 		}
 
 		if (is_fixup(item->command)) {
-			todo_list_release(&todo_list);
 			clear_commit_todo_item(&commit_todo);
 			return error(_("the script was already rearranged."));
 		}
@@ -4958,7 +4949,7 @@ int rearrange_squash(struct repository *r)
 				 *commit_todo_item_at(&commit_todo, commit2))
 				/* found by commit name */
 				i2 = *commit_todo_item_at(&commit_todo, commit2)
-					- todo_list.items;
+					- todo_list->items;
 			else {
 				/* copy can be a prefix of the commit subject */
 				for (i2 = 0; i2 < i; i2++)
@@ -4971,7 +4962,7 @@ int rearrange_squash(struct repository *r)
 		}
 		if (i2 >= 0) {
 			rearranged = 1;
-			todo_list.items[i].command =
+			todo_list->items[i].command =
 				starts_with(subject, "fixup!") ?
 				TODO_FIXUP : TODO_SQUASH;
 			if (next[i2] < 0)
@@ -4989,10 +4980,8 @@ int rearrange_squash(struct repository *r)
 	}
 
 	if (rearranged) {
-		struct strbuf buf = STRBUF_INIT;
-
-		for (i = 0; i < todo_list.nr; i++) {
-			enum todo_command command = todo_list.items[i].command;
+		for (i = 0; i < todo_list->nr; i++) {
+			enum todo_command command = todo_list->items[i].command;
 			int cur = i;
 
 			/*
@@ -5003,37 +4992,50 @@ int rearrange_squash(struct repository *r)
 				continue;
 
 			while (cur >= 0) {
-				const char *bol =
-					get_item_line(&todo_list, cur);
-				const char *eol =
-					get_item_line(&todo_list, cur + 1);
-
-				/* replace 'pick', by 'fixup' or 'squash' */
-				command = todo_list.items[cur].command;
-				if (is_fixup(command)) {
-					strbuf_addstr(&buf,
-						todo_command_info[command].str);
-					bol += strcspn(bol, " \t");
-				}
-
-				strbuf_add(&buf, bol, eol - bol);
-
+				ALLOC_GROW(items, nr + 1, alloc);
+				items[nr++] = todo_list->items[cur];
 				cur = next[cur];
 			}
 		}
 
-		res = rewrite_file(todo_file, buf.buf, buf.len);
-		strbuf_release(&buf);
+		FREE_AND_NULL(todo_list->items);
+		todo_list->items = items;
+		todo_list->nr = nr;
+		todo_list->alloc = alloc;
 	}
 
 	free(next);
 	free(tail);
-	for (i = 0; i < todo_list.nr; i++)
+	for (i = 0; i < todo_list->nr; i++)
 		free(subjects[i]);
 	free(subjects);
 	hashmap_free(&subject2item, 1);
-	todo_list_release(&todo_list);
 
 	clear_commit_todo_item(&commit_todo);
-	return res;
+
+	return 0;
+}
+
+int rearrange_squash_in_todo_file(struct repository *r)
+{
+	const char *todo_file = rebase_path_todo();
+	struct todo_list todo_list = TODO_LIST_INIT;
+	int res = 0;
+
+	if (strbuf_read_file_or_whine(&todo_list.buf, todo_file) < 0)
+		return -1;
+	if (todo_list_parse_insn_buffer(r, todo_list.buf.buf, &todo_list) < 0) {
+		todo_list_release(&todo_list);
+		return -1;
+	}
+
+	res = todo_list_rearrange_squash(&todo_list);
+	if (!res)
+		res = todo_list_write_to_file(r, &todo_list, todo_file, NULL, NULL, -1, 0);
+
+	todo_list_release(&todo_list);
+
+	if (res)
+		return error_errno(_("could not write '%s'."), todo_file);
+	return 0;
 }
diff --git a/sequencer.h b/sequencer.h
index 1d9d66b0cd..e680fe2daa 100644
--- a/sequencer.h
+++ b/sequencer.h
@@ -152,7 +152,7 @@ int complete_action(struct repository *r, struct replay_opts *opts, unsigned fla
 		    const char *shortrevisions, const char *onto_name,
 		    const char *onto, const char *orig_head, struct string_list *commands,
 		    unsigned autosquash);
-int rearrange_squash(struct repository *r);
+int rearrange_squash_in_todo_file(struct repository *r);
 
 extern const char sign_off_header[];
 
-- 
2.20.1